Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension
Naoya Inoue, Harsh Trivedi, Steven Sinha, Niranjan Balasubramanian, Kentaro Inui
Abstract
How can we generate concise explanations for multi-hop Reading Comprehension (RC)? The current strategies of identifying supporting sentences can be seen as an extractive question-focused summarization of the input text. However, these extractive explanations are not necessarily concise i.e. not minimally sufficient for answering a question. Instead, we advocate for an abstractive approach, where we propose to generate a question-focused, abstractive summary of input paragraphs and then feed it to an RC system. Given a limited amount of human-annotated abstractive explanations, we train the abstractive explainer in a semi-supervised manner, where we start from the supervised model and then train it further through trial and error maximizing a conciseness-promoted reward function. Our experiments demonstrate that the proposed abstractive explainer can generate more compact explanations than an extractive explainer with limited supervision (only 2k instances) while maintaining sufficiency.- Anthology ID:
- 2021.emnlp-main.490
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6064–6080
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.490
- DOI:
- 10.18653/v1/2021.emnlp-main.490
- Cite (ACL):
- Naoya Inoue, Harsh Trivedi, Steven Sinha, Niranjan Balasubramanian, and Kentaro Inui. 2021. Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6064–6080, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension (Inoue et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2021.emnlp-main.490.pdf
- Code
- stonybrooknlp/suqa
- Data
- CoLA, HotpotQA